|
| 基于BiLSTM的城市供水管网压力跟随算法研究 |
| Research on Pressure Following Algorithm of Water Supply Network based on BiLSTM Optimization |
| 投稿时间：2024-12-26 修订日期：2025-04-01 |
| DOI： |
| 中文关键词: 关键词：供水管网 压力跟随算法 BiLSTM 惩罚项 |
| 英文关键词: Key words: water supply network pressure following algorithm BiLSTM penalty term |
| 基金项目:安徽省高校科学研究重大项目（2024AH040039） |
|
| 摘要点击次数: 151 |
| 全文下载次数: 0 |
| 中文摘要: |
| 压力调控对城市供水管网的优化调度至关重要。因此，提出了基于多层双向长短期记忆神经网络（Bi-directional Long Short-Term Memory，BiLSTM）的压力跟随算法。首先，以麻雀搜索算法对BiLSTM的参数进行优化，寻找当前最优的超参数，从而更好的提高模型对压力的拟合精度。其次，对损失函数添加惩罚项，该惩罚项主要学习流量与压力之间的相关性，通过神经网络的不断迭代，对供水管网的压力进行优化。实验结果表明，经过压力跟随算法优化后的压力与流量同步变化，优化后的压力能够为供水管网的优化调度提供理论依据和支撑。 |
| 英文摘要: |
| Pressure regulation is crucial for optimal scheduling of urban water supply networks. This paper proposes a pressure-following algorithm based on a multi-layer bidirectional long short-term memory (Bi-LSTM) neural network. Firstly, the Sparrow Search Algorithm is used to optimize the parameters of the BiLSTM, searching for the optimal hyperparameters to better improve the fitting accuracy of pressure. Secondly, a penalty term which learn the correlation between traffic and stress is added to the loss function, and the neural network iteratively optimizes the pressure of the water supply network. The experimental results demonstrate that the optimized pressure, which varies in synchrony with the flow following the application of the pressure-following algorithm, provides a theoretical foundation and underpinning for the optimization of water supply network scheduling. |
|
View Fulltext
查看/发表评论 下载PDF阅读器 |
| 关闭 |
